© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18370
    Prev
    Next
    INDEX
    Explanations

    gloves or Glover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ°æľĢåIJİ
    -0.10
    weet
    -0.09
    缴éĢļ车
    -0.09
    -0.09
    nings
    -0.09
    æºIJæ³ī
    -0.09
    ment
    -0.09
    noon
    -0.09
    acing
    -0.08
    ÑģÑı
    -0.08
    POSITIVE LOGITS
    ened
    0.10
    å¯IJ
    0.10
    pedia
    0.09
    mith
    0.09
    iÄĻ
    0.09
    lege
    0.09
    еÑģ
    0.09
    Ñĥм
    0.09
    åĮ»ç§ij
    0.09
    æIJ¦
    0.09
    Activations Density 0.008%

    No Known Activations